© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39924
    Prev
    Next
    INDEX
    Explanations

    ПУ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.84
    SpringBootTest
    -0.69
    évaluateur
    -0.67
    featureID
    -0.67
    ArgsConstructor
    -0.65
     AssemblyTitle
    -0.65
    posedge
    -0.65
    GEBURTS
    -0.63
    WebVitals
    -0.63
    intenant
    -0.63
    POSITIVE LOGITS
     المعيارى
    0.46
     Ca
    0.44
     mac
    0.44
    olol
    0.44
    acs
    0.43
    organized
    0.43
    niv
    0.43
     Mac
    0.43
    以此
    0.43
    Ca
    0.42
    Activations Density 0.325%

    No Known Activations